© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65322
    Prev
    Next
    INDEX
    Explanations

    colorectal cancer and impotent patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŀ¶
    -0.07
    bud
    -0.06
    ROY
    -0.06
    ç²Ł
    -0.06
    ppo
    -0.06
    one
    -0.06
    ÙģÙī
    -0.06
     Conv
    -0.06
    å½¹
    -0.06
     UNIT
    -0.06
    POSITIVE LOGITS
    olz
    0.09
    ×Ļצ
    0.08
    blia
    0.07
    incu
    0.07
    ersen
    0.07
    ouses
    0.07
    ìm
    0.07
    ãĥĵãĤ¢
    0.07
     tò
    0.07
    人å¿ĥçļĦ
    0.07
    Activations Density 0.050%

    No Known Activations